Will vs Denzel

will.nmid = "nm0000226";
will.movies = IMDB.getMoviesForPerson(will.nmid);

denzel.nmid = "nm0000243";
denzel.movies = IMDB.getMoviesForPerson(denzel.nmid);

will.info = IMDB.getPersonInfo(will.nmid);
denzel.info = IMDB.getPersonInfo(denzel.nmid);

will.info

denzel.info

#POPULAR MOVIES FROM 1980 THROUGH 2020
popular50 = subsetDataFrame(imdb.data$movies$popular50, "year", ">=", 1980)
popular50 = subsetDataFrame(popular50, "year", "<=", 2020)
dim(popular50)

library(devtools);       # required for source_url
install_github("MonteShaffer/imdb/imdb");
#detach(package:imdb);
library(imdb);
packageVersion("imdb")
library(humanVerseWSU);

path.github = "https://raw.githubusercontent.com/MonteShaffer/humanVerseWSU/master/";


include.me = paste0(path.github, "misc/functions-nlp.R");
source_url( include.me );
include.me = paste0(path.github, "misc/functions-nlp-str.R");
source_url( include.me );
include.me = paste0(path.github, "misc/functions-nlp-stack.R");
source_url( include.me );
include.me = paste0(path.github, "misc/functions-nlp-pos.R");
source_url( include.me );
include.me = paste0(path.github, "humanVerseWSU/R/functions-encryption.R");
source_url( include.me );
###### UPDATES TO dataframe subset function ######
# inflation adjustments for NA ... and improvements on subsetting
include.me = paste0(path.github, "humanVerseWSU/R/functions-dataframe.R");
source_url( include.me );
include.me = paste0(path.github, "humanVerseWSU/R/functions-inflation.R");
source_url( include.me );

# path to project
path.project = "C:/_git_/WSU_STATS419_FALL2020/final/";

library(dplyr)
library(ggplot2)
library(gridExtra)
library(Hmisc)
library(knitr)
library(tidyr)

will.n = nrow(will.movies);
will.movies.r = replaceFactorColumnWithIndicatorVariables(will.movies, "genre", "genre", use.boolean=FALSE);
# colSums(will.cast.info.r[,11:34]);
will.genre.p = sort(colSums(will.movies.r[,7:24])/will.n, decreasing = TRUE);  # proportion by movie
will.genre.p
denzel.n = nrow(denzel.movies);
denzel.movies.r = replaceFactorColumnWithIndicatorVariables(denzel.movies, "genre", "genre", use.boolean=FALSE);
# colSums(will.cast.info.r[,11:34]);
denzel.genre.p = sort(colSums(denzel.movies.r[,7:22])/denzel.n, decreasing = TRUE);  # proportion by movie
denzel.genre.p

# 
# g <-ggplot(sub.data.long, aes(x=as.factor(ttid))) +
#   geom_bar(aes(fill=as.factor(type)), width = 0.5)+
#   theme(axis.text.x = element_text(angle = 65, vjust = 0.6)) 
# g

library(xtable)
library(table1)

will.table = will.popular[,c(3,5,4,9,11,14)]
will.table = will.table[with(will.table,order(rank)),]

denzel.table = denzel.popular[,c(3,5,4,9,11,14)]
denzel.table = denzel.table[with(denzel.table,order(rank)),]

print(xtable(will.table, type = "latex"), file = "tables/will.table.tex")
#print(xtable(denzel.table, type = "latex"), file = "tables/denzel.table.tex")

# label(will.denzel.merge$ratings) <- "ratings"
# label(will.denzel.merge$votes) <- "votes"
# label(will.denzel.merge$rank.popular) <- "rank.popular"
# table1(~ratings + votes + rank.popular | nmid, data = will.denzel.merge)

library(kableExtra)
#webshot::install_phantomjs(force = TRUE)
# df <- will.popular[,c(9,11,41:48)]
# d <- summary(df)
# d %>%
#   kbl(format="latex",caption = "Descriptive analyse of Will Smith popular 50",booktabs = TRUE) %>%
#   kable_classic(full_width = T, html_font = "Cambria")
# 
# print(xtable(d,"latex"), file="tables/test.tex")